@inproceedings{imperial-2022-nu,
title = "{NU} {HLT} at {CMCL} 2022 Shared Task: Multilingual and Crosslingual Prediction of Human Reading Behavior in Universal Language Space",
author = "Imperial, Joseph Marvin",
editor = "Chersoni, Emmanuele and
Hollenstein, Nora and
Jacobs, Cassandra and
Oseki, Yohei and
Pr{\'e}vot, Laurent and
Santus, Enrico",
booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.cmcl-1.12",
doi = "10.18653/v1/2022.cmcl-1.12",
pages = "108--113",
abstract = "In this paper, we present a unified model that works for both multilingual and crosslingual prediction of reading times of words in various languages. The secret behind the success of this model is in the preprocessing step where all words are transformed to their universal language representation via the International Phonetic Alphabet (IPA). To the best of our knowledge, this is the first study to favorably exploit this phonological property of language for the two tasks. Various feature types were extracted covering basic frequencies, n-grams, information theoretic, and psycholinguistically-motivated predictors for model training. A finetuned Random Forest model obtained best performance for both tasks with 3.8031 and 3.9065 MAE scores for mean first fixation duration (FFDAvg) and mean total reading time (TRTAvg) respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imperial-2022-nu">
<titleInfo>
<title>NU HLT at CMCL 2022 Shared Task: Multilingual and Crosslingual Prediction of Human Reading Behavior in Universal Language Space</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">Marvin</namePart>
<namePart type="family">Imperial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Hollenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassandra</namePart>
<namePart type="family">Jacobs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Oseki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Prévot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a unified model that works for both multilingual and crosslingual prediction of reading times of words in various languages. The secret behind the success of this model is in the preprocessing step where all words are transformed to their universal language representation via the International Phonetic Alphabet (IPA). To the best of our knowledge, this is the first study to favorably exploit this phonological property of language for the two tasks. Various feature types were extracted covering basic frequencies, n-grams, information theoretic, and psycholinguistically-motivated predictors for model training. A finetuned Random Forest model obtained best performance for both tasks with 3.8031 and 3.9065 MAE scores for mean first fixation duration (FFDAvg) and mean total reading time (TRTAvg) respectively.</abstract>
<identifier type="citekey">imperial-2022-nu</identifier>
<identifier type="doi">10.18653/v1/2022.cmcl-1.12</identifier>
<location>
<url>https://aclanthology.org/2022.cmcl-1.12</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>108</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NU HLT at CMCL 2022 Shared Task: Multilingual and Crosslingual Prediction of Human Reading Behavior in Universal Language Space
%A Imperial, Joseph Marvin
%Y Chersoni, Emmanuele
%Y Hollenstein, Nora
%Y Jacobs, Cassandra
%Y Oseki, Yohei
%Y Prévot, Laurent
%Y Santus, Enrico
%S Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F imperial-2022-nu
%X In this paper, we present a unified model that works for both multilingual and crosslingual prediction of reading times of words in various languages. The secret behind the success of this model is in the preprocessing step where all words are transformed to their universal language representation via the International Phonetic Alphabet (IPA). To the best of our knowledge, this is the first study to favorably exploit this phonological property of language for the two tasks. Various feature types were extracted covering basic frequencies, n-grams, information theoretic, and psycholinguistically-motivated predictors for model training. A finetuned Random Forest model obtained best performance for both tasks with 3.8031 and 3.9065 MAE scores for mean first fixation duration (FFDAvg) and mean total reading time (TRTAvg) respectively.
%R 10.18653/v1/2022.cmcl-1.12
%U https://aclanthology.org/2022.cmcl-1.12
%U https://doi.org/10.18653/v1/2022.cmcl-1.12
%P 108-113
Markdown (Informal)
[NU HLT at CMCL 2022 Shared Task: Multilingual and Crosslingual Prediction of Human Reading Behavior in Universal Language Space](https://aclanthology.org/2022.cmcl-1.12) (Imperial, CMCL 2022)
ACL